12321234

Energy Efficient Storage of Error-Correction-Detection Information

PublishedJune 3, 2025
Assigneenot available in USPTO data we have
Technical Abstract

Patent Claims
20 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A controller, comprising: at least three memory channel interfaces that are to operate independently of accesses that occur via the other of the at least three memory channel interfaces, the at least three memory channel interfaces including a first memory channel interface, a second memory channel interface, and an error detection and correction channel interface, the first memory channel interface to access a first data word group that is stored contiguously in a first row of a first memory device coupled to the first memory channel interface concurrently with the error detection and correction channel interface accessing a first set of check bits associated with the first data word group and a second set of check bits associated with a second data word group that is stored contiguously in a second row of a second memory device coupled to the second memory channel interface; and an error detection and correction data cache to cache the second set of check bits that was accessed concurrently with the first data word group.

2

2. The controller of claim 1, wherein the an error detection and correction data cache is to also cache the first set of check bits that was accessed concurrently with the first data word group.

3

3. The controller of claim 1, wherein the first set of check bits and the second set of check bits are stored in a third row of a memory device coupled to the error detection and correction channel interface.

4

4. The controller of claim 3, wherein a first row address addresses the first row, a second row address addresses the second row, and a third row address addresses the third row.

5

5. The controller of claim 4, wherein the third row address is not equal to the first row address.

6

6. The controller of claim 5, wherein the third row address is not equal to the second row address.

7

7. The controller of claim 2, wherein the at least three memory channel interfaces each include command, address, and data transfer functions that operate independently of the command, address, and data transfer functions of other ones of the at least three memory channel interfaces.

8

8. A controller, comprising: a plurality of memory channel interfaces that are to access a respective plurality of memory components independently of accesses to others of the respective plurality of memory components via the other memory channel interfaces, the plurality of memory channel interfaces including an error detection and correction data channel interface to open a row storing a first group of check bits and a second group of check bits stored in an error detection and correction (EDC) memory component that is a first one of the respective plurality of memory components, the first group of check bits used to check data stored in a first single row, addressed by a first row address, of a first data memory component accessed via a first one of the plurality of memory channel interfaces, the first data memory component being a second one of the respective plurality of memory components, the second group of check bits to be used to check data stored in a second single row, addressed by a second row address, of a second data memory component accessed via a second one of the plurality of memory channel interfaces, the second data memory component being a third one of the respective plurality of memory components, where the first single row is accessed while the row storing the first group of check bits and the second group of check bits is open; and an error detection and correction data cache to cache the second set of check bits by accessing the second set of check bits based on the row storing the first group of check bits and the second group of check bits being open to access the first single row to access the first group of check bits.

9

9. The controller of claim 8, wherein the controller is to concurrently access the first group of check bits and the second group of check bits.

10

10. The controller of claim 8, wherein the row storing the first group of check bits and the second group of check bits is addressed by a third row address.

11

11. The controller of claim 10, wherein the first row address and the third row address are not equal.

12

12. The controller of claim 11, wherein the second row address and the third row address are not equal.

13

13. The controller of claim 10, wherein the first row address and the third row address are equal.

14

14. The controller of claim 13, wherein the second row address and the third row address are equal.

15

15. A method of operating a controller, comprising: opening, via an error detection and correction (EDC) channel interface, a first EDC row of an EDC memory device coupled to the EDC channel interface, the first EDC row storing a first set of check bits and a second set of check bits; accessing, while the first EDC row is open and via a first memory channel interface coupled to a first memory channel, a first data word group that is stored contiguously by a first row of a first memory component that is coupled to the first memory channel, the first row addressed by a first row address; accessing, while the first EDC row is open via the EDC channel interface, the first set of check bits from the first EDC row; accessing, while the first EDC row is open to access the first set of check bits and via the EDC channel interface, the second set of check bits from the first EDC row; caching the second set of check bits in an error detection and correction data cache; and using the first set of check bits to check the first data word group.

16

16. The method of claim 15, further comprising: based on accessing the first set of check bits to check the first data word group, caching the first set of check bits in the error detection and correction data cache.

17

17. The method of claim 15, wherein the first set of check bits and the second set of check bits are accessed concurrently from the first EDC row.

18

18. The method of claim 15, wherein the first EDC row of the EDC memory device is not addressed by the first row address.

19

19. The method of claim 15, wherein a second data word group that is stored contiguously by a second row of a second memory component that is coupled to a second memory channel is checked by the second set of check bits.

20

20. The method of claim 15, wherein the first EDC row is addressed by the first row address.

Patent Metadata

Filing Date

Unknown

Publication Date

June 3, 2025

Inventors

Michael Raymond MILLER
Stephen Magee
John Eric Linstadt

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “ENERGY EFFICIENT STORAGE OF ERROR-CORRECTION-DETECTION INFORMATION” (12321234). https://patentable.app/patents/12321234

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.

ENERGY EFFICIENT STORAGE OF ERROR-CORRECTION-DETECTION INFORMATION — Michael Raymond MILLER | Patentable